Rilevamento delle anomalie

Rilevare anomalie del segnale utilizzando modelli di intelligenza artificiale, comprese le reti di Deep Learning

Estrai caratteristiche sparse tempo-frequenza per rilevare anomalie nei dati elettromagnetici, acustici e di vibrazione.

Funzioni

deepSignalAnomalyDetector Create signal anomaly detector (Da R2023a)

`audioDatastore`	Datastore for collection of audio files
`arrayDatastore`	Datastore for in-memory data
`signalDatastore`	Datastore for collection of signals
`imageDatastore`	Datastore for image data
`waveletScattering`	Wavelet time scattering
`signalTimeFeatureExtractor`	Streamline signal time feature extraction (Da R2021a)
`signalFrequencyFeatureExtractor`	Streamline signal frequency feature extraction (Da R2021b)
`signalTimeFrequencyFeatureExtractor`	Streamline signal time-frequency feature extraction (Da R2024a)
`stftLayer`	Short-time Fourier transform layer (Da R2021b)
`istftLayer`	Inverse short-time Fourier transform layer (Da R2024a)
`cwtLayer`	Continuous wavelet transform layer (Da R2022b)
`icwtLayer`	Inverse continuous wavelet transform layer (Da R2024b)
`modwtLayer`	Maximal overlap discrete wavelet transform layer (Da R2022b)

Detect anomalies in acoustic data using wavelet scattering and the deepSignalAnomalyDetector object.

Use autoencoders to detect abnormal points or segments in time-series data.

Use a long short-term memory autoencoder to detect anomalies in data from an industrial machine.

Use wavelet and deep learning techniques to detect and localize transverse pavement cracks.

(Deep Learning Toolbox)

Learn how to develop an alert system for predictive maintenance using wavelet scattering and deep learning.

(Deep Learning Toolbox)

Classify faults in acoustic recordings of air compressors using a wavelet scattering network paired with a recurrent neural network.

(Deep Learning Toolbox)